Ioannis Pitas

TL;DR: This paper proposes a new scalable solution for the Least Squares One-Class Support Vector Machine classifier by following an approximate kernel approach and evaluated the proposed method in big data visual classification problems, where it is shown that it is able to achieve satisfactory performance, while significantly reducing the overall computational and memory costs.

TL;DR: A new method for detecting shot boundaries in video sequences by fusing features obtained by singular value decomposition (SVD) and mutual information (MI) is proposed, which can detect cuts and gradual transitions, such as dissolves, fades and wipes.

TL;DR: The present paper describes an extension to the methods proposed by Sobottka and Pitas for the extraction of facial features with the ultimate goal to be used in defining a sufficient set of distances between them so that a unique description of the structure of a face is obtained.

TL;DR: A novel set of multiplicative update rules is proposed, which is independent from any kind of learning rate parameter, provides computational efficiency compared to the conventional batch training approach and is easy to implement.

TL;DR: In this work, semantic shot selection based on the narrative prominence of movie characters in both the visual and the audio modalities is investigated, without the need for additional data such as a script.